Employing Wikipedia's Natural Intelligence For Cross Language Information Retrieval

TL;DR

This paper introduces a novel cross-language information retrieval method leveraging Wikipedia's multilingual content as an intermediary, offering an alternative to traditional machine translation-based techniques and demonstrating its effectiveness.

Contribution

The paper presents a new approach that uses Wikipedia as a multilingual intermediary for cross-language information retrieval, bypassing the need for machine translation.

Findings

Wikipedia-based method improves retrieval accuracy

Comparable performance to machine translation approaches

Applicable to multiple languages without translation tools

Abstract

In this paper we present a novel method for retrieving information in languages other than that of the query. We use this technique in combination with existing traditional Cross Language Information Retrieval (CLIR) techniques to improve their results. This method has a number of advantages over traditional techniques that rely on machine translation to translate the query and then search the target document space using a machine translation. This method is not limited to the availability of a machine translation algorithm for the desired language and uses already existing sources of readily available translated information on the internet as a "middle-man" approach. In this paper we use Wikipedia; however, any similar multilingual, cross referenced body of documents can be used. For evaluation and comparison purposes we also implemented a traditional machine translation approach separately as well as the Wikipedia approach separately.